The practice and study of investments have a long stand in human history. Not until the recent emergence and growth of the modern financial industry did we start to observe sophisticated and systematic investment management practices. Utilizing financial instruments and tools to make thoughtful investment decisions is becoming mainstream among various investment activities. At the same time, the forms of investments have undergone essential changes. Traditional model-driven investment methods are inevitably confronted with challenges. With the popularization of computer and network technology, most data related to financial investment activities becomes traceable and is rapidly accumulated into a substantial volume. More and more data-driven investment methods are emerging and demonstrate vigorous vitality. However, we need to realize that, even with the emergence of "big data", we are still far from the age of real "smart" investment. The research on data-driven investment strategy has significant implications in both theoretical and practical senses.
Big data technology provides a diversified source of information for investment strategies, which can help us get an objective and effective analysis when faced with a plethora of market information, including but not limited to macroeconomic data, corporate financial data, records of trading activities. Compared with traditional data, other forms of data such as social network information, regional weather conditions, and commercial transportation data can, from a distinct perspective, help filter out "information noise" and present a more comprehensive landscape view on the investment decision-making process. In this context, the problem is how to fully utilize heterogeneous "big data" to optimize financial investment strategies in regards to, for example, asset pricing, portfolio management, and financial products marketing strategy.
Moreover, the rapid advance of cutting-edge artificial intelligence technology provides potentially promising solutions to data-driven investment strategies. It is visible that data-intensive AI models are increasingly employed in various domains (e.g., computer vision, image recognition, speech understanding) and make essential improvements. Therefore, this Research Topic aims to welcome the latest impactful contributions to data-driven analytical research on investment strategy.
In recent years, we have witnessed a couple of interesting research directions on data-driven investment strategies. One line of stimulating studies is about stock price prediction using innovative artificial intelligence models, such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Graph Neural Networks (GNN). Another strain of work relates to developing distinctive risk assessment models or portfolio optimization algorithms to facilitate better investment decision-making in existing or emerging financial markets, e.g., P2P lending. Meanwhile, other intriguing work is rising, like stock market anomaly detection using GNN models or NLP model-based financial statements for fraud detection.
To be more specific, we call for inspiring and solid studies on the topics below, including but not limited to:
● Improvement and optimization of traditional asset pricing models
● Research on the effectiveness of market anomaly factors
● Financial big data analysis based on data mining technology
● Research on fraud in financial statements of listed companies
● Research on stock price prediction based on expert information
● Research on stock price prediction based on multi-source information fusion
● Fundamental quantitative investment
● The impact of trading behaviors of different investor types on stock prices
● Research on the long-term value of listed companies based on financial fundamentals
● Identification and optimization of financial big data concept drift
● Local optimization problems in financial data mining
● Improvement of investment portfolio optimization using multi-source data
● The value analysis, discovery, and collaborative creation mechanism of financial big data based on knowledge association
● Other topics in data-driven investment strategies
Submission deadline: 31 July 2021
All submitted articles are peer reviewed.
All published articles are subject to article processing charges. We work with numerous institutions to ensure researchers are supported when publishing open access.
Editorial team:
Dr. Chuanren Liu, The University of Tennessee, Knoxville, Knoxville, United States
Dr. Hao Zhong, ESCP Europe, Paris, France
Dr. Yanhong Guo, Faculty of Management and Economics, Dalian University of Technology, Dalian, China
For more details, please refer to: https://www.frontiersin.org/research-topics/18634/data-driven-investment-strategies
Looking forward to receiving your manuscripts. Thank you!
Best regards,
------------------------------
Howard Zhong
Assistant Professor
ESCP Business School
------------------------------